Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/textura-agency/next16-claude-starterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/textura-agency/next16-claude-starter/qa)<a href="https://agentmods.dev/commands/textura-agency/next16-claude-starter/qa"><img src="https://agentmods.dev/badge/commands/textura-agency/next16-claude-starter/qa/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/textura-agency/next16-claude-starter/qa"><img src="https://agentmods.dev/badge/commands/textura-agency/next16-claude-starter/qa.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.00383 |
| Opus 5.5 | $0.00007 | $0.00153 |
| Sonnet 5.5 | $0.00004 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
qa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 21d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run verification on: $ARGUMENTS (whole src/ if empty).
Use the qa-verify skill. In short:
.claude/scripts/verify.sh $ARGUMENTS— every FAIL must be fixed; WARNs are fixed or explicitly justified.yarn lint,npx tsc --noEmit -p .andyarn build.- The judgement pass: design fidelity against a re-fetched Figma node, token discipline, motion primitive choice, semantics and a11y, responsive behaviour down to 320px, architecture (routes delegate, server-first, props not hardcoded content).
- The browser pass on
yarn start(yarn qa:setuponce; person's UA, look at every screenshot):node tools/qa/axe-sweep.mjs --url …— contrast/target-size through the entrance, not just at restnode tools/qa/resize-check.mjs --url …— live resizes and DevTools device-preset switches land where a fresh load doesnode tools/qa/check-motion.mjs --url …— reduced motion and the robot form don't hangscrollWidth === innerWidthat 320–430; overlays in dark scheme too- anything a phone shows changed →
/mobile
- Fix, then re-run from step 1 until clean.
Report what failed, what you fixed, what you consciously left, and anything you could not verify (no design, no real device, iOS-only behaviour).
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 21d ago Changed · +10 lines · +7 tokens per session 77d2764a348d
- 1mo ago First seen · 21 lines · 11 tokens per session scan A 2332d1ab2455
qa is a command published in the GitHub repository textura-agency/next16-claude-starter (139 stars, last pushed 13d ago), licensed Unlicense. It adds 18 tokens to every session and 383 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
ux-grill
Use when a running web app's UX has to be audited reproducibly rather than by feel — a deterministic mechanical pass over routes and viewports (axe, target size, horizontal overflow, page title, scripted journeys) followed by a screenshot-grounded interrogation of the operator, journey by journey, with two persona…
p3-ux-a11y
Defines WCAG target, contrast requirements, keyboard navigation, screen reader requirements and testing methods.
audit-visual-consistency
Use this command to validate design token compliance (single image mode) or detect visual regressions (regression mode).
kmp-audit-design-visual
Runs a visual-only audit of your app's Roborazzi screenshots using Claude vision.
playwright-test-heal
Run all my tests and fix the failing ones.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.